A Surface Quality Management Method for a Stator Core Mold

Abstract

The present application relates to the technical field of data processing, and provides a surface quality management method for a stator core mold. The method includes: performing surface quality detection on a target stator core mold to obtain a quality deviation coefficient; performing multi-dimensional verification based on the deviation coefficient to output multiple quality management levels; constructing a teacher model by hierarchical association; obtaining a goodness distillation result by optimizing the model through a knowledge distillation channel and branches; and accordingly constructing a student model to optimize the surface quality management of the stator core mold. The present application solves the technical problem that traditional detection methods often rely on manual experience and visual observation, only focus on the roughness and smoothness of the mold surface, and it is difficult to accurately evaluate the actual quality of the mold surface, resulting in low accuracy and stability of quality management. Through comprehensive measures in multiple links such as a knowledge distillation channel and a quality management teacher model, the technical effects of improving the surface quality of the mold and improving the accuracy and efficiency of quality management are achieved.

Description

Technical Field

[0001] This application relates to the field of computer science and technology, specifically to the field of data processing technology, and particularly to a surface quality management method for a stator core mold. Background Art

[0002] With the continuous progress of industrial technology and the rapid development of intelligent manufacturing, the surface quality management of stator core molds has become a key factor affecting product quality and production efficiency. However, there are many deficiencies in traditional surface quality management methods for stator core molds. Traditional detection methods mainly rely on manual experience and visual inspection. This method is highly subjective, inefficient, and difficult to accurately evaluate the actual quality of the mold surface. At the same time, traditional surface quality management methods often only focus on appearance indicators such as the roughness and smoothness of the mold surface, while ignoring more critical factors such as wear resistance and corrosion resistance. These factors are crucial for the service life of the mold and the quality of the stator core. Due to the lack of comprehensive consideration of these key factors, traditional methods cannot effectively prevent problems such as wear and corrosion that may occur during the use of the mold, affecting the overall performance and stability of the mold, and thus resulting in low accuracy and stability in mold quality management. Summary of the Invention

[0003] This application provides a surface quality management method for a stator core mold, aiming to solve the technical problem that traditional detection methods often rely on manual experience and visual inspection, only focus on the roughness and smoothness of the mold surface, and are difficult to accurately evaluate the actual quality of the mold surface, resulting in low accuracy and stability in quality management.

[0004] In view of the above problems, this application provides a surface quality management method for a stator core mold.

[0005] This application provides a surface quality management method for a stator core mold. The method includes: performing surface quality detection on a target stator core mold to obtain a quality deviation coefficient; performing multi-dimensional verification based on the quality deviation coefficient and outputting N quality management levels, where N is an integer greater than or equal to 1; constructing a quality management teacher model by connecting the N quality management levels according to the hierarchical association relationship; optimizing the quality management teacher model through a knowledge distillation channel, where the knowledge distillation channel includes N distillation goodness branches; performing data distillation on the N quality management levels through the N distillation goodness branches to obtain N goodness distillation results; constructing a quality management student model based on the N goodness distillation results, and performing optimized management of the surface quality of the target stator core mold through the quality management student model.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The above surface quality management method for a stator core mold detects the surface quality of the target stator core mold to obtain the quality deviation coefficient of the mold surface. Subsequently, multi-dimensional verification and analysis are carried out using the quality deviation coefficient to evaluate the surface quality of the mold from different angles and output multiple quality management levels. Then, according to the correlation between these quality management levels, they are connected together to construct a quality management teacher model. To make the quality management teacher model more efficient and accurate, knowledge distillation technology is introduced to optimize the quality management teacher model through the knowledge distillation channel. Then, multiple distillation goodness branches in the knowledge distillation channel are used to perform data distillation on multiple quality management levels, and combined with the optimization results of the quality management teacher model, multiple goodness distillation results are obtained. Finally, based on these results, a quality management student model is constructed. This quality management student model is then used to optimize the surface quality management of the target stator core mold. In this way, it can be ensured that the surface quality of the mold meets higher standards, thereby improving the performance and reliability of the stator core.

[0008] The above description is only an overview of the technical solution of this application. In order to be able to more clearly understand the technical means of this application, it can be implemented in accordance with the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically given below. Brief Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0010] Figure 1 It is a schematic flowchart of a surface quality management method for a stator core mold in an embodiment;

[0011] Figure 2 It is a schematic diagram for obtaining the quality deviation coefficient of a surface quality management method for a stator core mold in an embodiment. Detailed Description of the Embodiments

[0012] By providing a surface quality management method for a stator core mold in the embodiments of this application, it aims to solve the technical problems that traditional detection methods often rely on manual experience and visual observation, only focus on the roughness and smoothness of the mold surface, and it is difficult to accurately evaluate the actual quality of the mold surface, resulting in low accuracy and stability of quality management.

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0014] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0015] Embodiment 1

[0016] As Figure 1 、 Figure 2 shown, the present application provides a surface quality management method for a stator core mold, and the method includes:

[0017] Performing surface quality inspection on the target stator core mold to obtain a quality deviation coefficient;

[0018] With the rapid development of the power industry and continuous technological progress, the stator core mold, as a core component in motor manufacturing, its surface quality plays a crucial role in the performance and stability of the motor. However, in the current industrial production environment, the surface quality management of the stator core mold faces many challenges.

[0019] In the embodiments of the present application, the system terminal performs surface quality inspection on the target stator core mold, mainly to find out the differences between the mold surface and the ideal state. This process involves inspecting the roughness, warpage, finish, and coating uniformity of the mold, and obtaining the corresponding data in each inspection direction. Subsequently, the obtained data is used to calculate the deviation from the corresponding standard, and the calculation results are summarized to obtain the quality deviation coefficients, which can quantitatively reflect the quality status of the mold surface and help understand whether there are defects, unevenness, or other problems on the mold surface. Generally speaking, the process of performing surface quality inspection on the target stator core mold is to find out potential problems of the target stator core mold and provide a basis for subsequent optimization management.

[0020] Furthermore, the present application provides a method for performing surface quality inspection on the target stator core mold to obtain a quality deviation coefficient, and the method further includes:

[0021] Traverse the qualified die parameters of the stator core for big data, and formulate the surface quality inspection standards for the target stator core die. The surface quality inspection standards include a preset roughness standard, a preset warpage standard, a preset finish standard, and a preset coating uniformity standard;

[0022] Preferably, the system terminal uses big data to collect the qualified die parameter data of the stator core from different manufacturers, production batches, and usage environments, and classifies and organizes the collected data to ensure the accuracy and integrity of the data. Subsequently, traverse the roughness, warpage, finish, coating uniformity and other parameters of many qualified stator core dies from the collected data. Through the analysis of these parameters, comprehensively understand the performance of the qualified die in all aspects. Based on these analysis results, formulate the surface quality inspection standards for the target stator core die, and clarify the numerical range of each standard. The surface quality inspection standards include multiple dimensions, such as the preset roughness standard, the preset warpage standard, the preset finish standard, and the preset coating uniformity standard, etc. These standards not only help the system terminal clarify the level that the surface quality of the qualified die should reach, but also provide a clear basis and reference for the subsequent die surface quality inspection. In summary, by analyzing a large amount of data, formulating a comprehensive and detailed surface quality inspection standard can ensure the normal progress of the subsequent surface quality inspection of the stator core die.

[0023] Detect the target stator core die based on the preset roughness standard in the first detection stage, and generate a first detection result;

[0024] Detect the target stator core die based on the preset warpage standard in the second detection stage, and generate a second detection result;

[0025] Preferably, when the system terminal detects the surface quality of the target stator core die, it first conducts the first detection stage. In this stage, first compare the roughness data of the target stator core die with the preset roughness standard one by one. Judge whether each data point falls within the preset qualified range. For the roughness data within the qualified range, record it as qualified roughness. For the roughness data exceeding the qualified range, record it as unqualified roughness. Then sort and classify the recorded qualified and unqualified roughness to obtain the first detection result. After the first detection stage is completed, the system terminal starts the second detection stage. In this stage, use the same method to compare the warpage data with the preset warpage standard, detect whether there are defects such as unevenness and scratches, and record the qualified warpage and the specific position, size, and severity of the unqualified defects to generate the second detection result. In summary, these two detection stages accurately detect the roughness and warpage of the die respectively and generate corresponding detection results. These results will provide an important basis for subsequent quality analysis and optimization.

[0026] In the third inspection stage, the target stator core mold is inspected based on the preset finish standard to generate a third inspection result;

[0027] In the fourth inspection stage, the target stator core mold is inspected based on the preset coating uniformity standard to generate a fourth inspection result;

[0028] Preferably, the system terminal uses the same method as described above to obtain the same first inspection result and second inspection result. In the third inspection stage and the fourth inspection stage, the finish and coating uniformity of the target stator core mold are respectively compared using the preset finish standard and the preset coating uniformity standard, and the relevant data of qualified and unqualified are recorded to obtain the third inspection result and the fourth inspection result. Among them, the finish refers to the measure of the smoothness and cleanliness of the mold surface, which directly affects the quality and appearance of the mold. The higher the finish, the smoother and cleaner the mold surface, which is beneficial to the relevant operations of mold surface treatment. The coating uniformity refers to the degree of uniform distribution of the coating on the mold surface, that is, the consistency of the coating thickness or coating amount distribution within the coating area. The better the coating uniformity, the smaller the difference in coating thickness at different parts, thereby improving the service life and appearance quality of the mold. In summary, the third inspection stage and the fourth inspection stage respectively conduct precise and comprehensive inspections on the finish and coating uniformity of the mold and generate corresponding inspection results. These results not only provide the system terminal with the specific performance of the mold in key quality indicators but also provide strong data support for the subsequent acquisition of the quality deviation coefficient.

[0029] Integrate the first inspection result, the second inspection result, the third inspection result, and the fourth inspection result to perform deviation calculation, generating first quality deviation data, second quality deviation data, third quality deviation data, and fourth quality deviation data;

[0030] Add the first quality deviation data, the second quality deviation data, the third quality deviation data, and the fourth quality deviation data to the quality deviation coefficient.

[0031] Preferably, after the detection of the four key quality indicators of the target stator core mold, namely roughness, warpage, finish, and coating uniformity, the system terminal obtained four groups of detection results, namely the first detection result, the second detection result, the third detection result, and the fourth detection result. These results respectively reflect the performance of the mold in different quality dimensions. Subsequently, in order to more accurately evaluate the quality status of the mold, the system terminal performed deviation calculations. Specifically, the system terminal calculated the difference between all unqualified indicators in each detection result and their corresponding preset standards, and then calculated the ratio with the corresponding preset standards to obtain multiple roughness deviation coefficients, multiple warpage deviation coefficients, multiple finish deviation coefficients, and multiple uniformity deviation coefficients. Subsequently, the obtained multiple roughness deviation coefficients, multiple warpage deviation coefficients, multiple finish deviation coefficients, and multiple uniformity deviation coefficients were sorted and classified to obtain the first quality deviation data, the second quality deviation data, the third quality deviation data, and the fourth quality deviation data. These deviation data quantitatively reflect the gap between the mold and the standard in each detection index. After that, the system terminal added these four groups of quality deviation data to the quality deviation coefficient. The quality deviation coefficient is a comprehensive index that integrates the deviation information of the mold in multiple quality dimensions, thus providing a comprehensive quality evaluation perspective for the system terminal. By analyzing the quality deviation coefficient, the overall quality status of the mold can be better understood, potential quality problems can be identified, enabling a more comprehensive and accurate assessment of the quality status of the target stator core mold and providing data support for subsequent quality management.

[0032] Perform multi-dimensional verification based on the quality deviation coefficient and output N quality management levels, where N is an integer greater than or equal to 1;

[0033] In one embodiment, the system terminal performs multi-dimensional verification and analysis based on the calculated quality deviation coefficient, and then outputs multiple quality management levels. This is to comprehensively evaluate the quality status of the stator core mold from multiple angles and levels, ensuring that each link is effectively monitored and managed. The process of multi-dimensional verification is actually an in-depth analysis and interpretation of the quality deviation coefficient. Starting from the first quality deviation data, the second quality deviation data, the third quality deviation data, and the fourth quality deviation data, the system terminal draws relevant curves for dimension verification, and assigns different weights to the four drawn curves according to factors such as the severity of quality problems and the verification results, and then outputs N quality management levels. These quality management levels represent different levels of quality monitoring and management, from basic quality control to advanced quality optimization, and each level has its specific goals and requirements. By implementing these different levels of quality management, comprehensive control of the quality of the stator core mold can be achieved, ensuring that the requirements of the preset standards are met. Generally speaking, multi-dimensional verification based on the quality deviation coefficient and outputting multiple quality management levels can help the system terminal better understand the quality status of the mold, identify potential problems, and improve the quality of the mold.

[0034] Furthermore, the present application provides a method for performing multi-dimensional verification based on the quality deviation coefficient and outputting N quality management levels, and the method further includes:

[0035] Analyze the change trends of the first quality deviation data, the second quality deviation data, the third quality deviation data, and the fourth quality deviation data respectively, and obtain the first quality change curve, the second quality change curve, the third quality change curve, and the fourth quality change curve;

[0036] Optionally, in surface quality inspection, the system terminal separately obtains the first quality deviation data, the second quality deviation data, the third quality deviation data, and the fourth quality deviation data, which respectively represent the quality deviation conditions of the stator core mold in different inspection stages and different inspection indicators. To more intuitively understand the change trends of these deviation data, the system terminal further analyzes these data and plots the corresponding quality change curves. First, for the first quality deviation data, the system terminal marks the roughness deviation coefficients in the first quality deviation data in the coordinate system according to the corresponding batch information. Each data point represents the quality deviation value of a batch. Subsequently, the cubic spline interpolation method is used to calculate the parameters of the curve in each interval. This involves solving the corresponding system of linear equations to determine the polynomial coefficients of the curve in each interval. After that, using these parameters, polynomial functions are constructed in each interval, and these functions are connected to form the overall spline interpolation curve, that is, the first quality change curve. This curve shows the fluctuation of the quality deviation of the mold in roughness inspection. By observing the undulation and slope of the curve, it can be judged whether the mold quality is stable in this link and whether there are obvious quality problems. Then, the system terminal uses the same method to analyze the second, third, and fourth quality deviation data and plots the second, third, and fourth quality change curves respectively. These curves respectively reflect the quality change conditions of the mold in other inspection links and indicators. By comparing the shapes and characteristics of different curves, the quality performance differences of the mold in different aspects can be judged, so as to find out possible quality problems or weak links. In summary, through the analysis of the first, second, third, and fourth quality deviation data and the plotting of the corresponding quality change curves, the quality change conditions of the stator core mold in multiple aspects can be comprehensively and intuitively understood.

[0037] Determine a verification dimension based on the first quality change curve, the second quality change curve, the third quality change curve, and the fourth quality change curve;

[0038] Test and record the quality deviation coefficients according to the verification dimension to generate a multi-dimensional verification result;

[0039] Optionally, the system terminal conducts a detailed characteristic analysis on each quality change curve. This includes analyzing the overall trend of the curve, the positions of peaks and valleys, the slope changes of the curve, etc. These characteristics can reflect the variation rules of quality deviations under different detection links and indicators. Based on the curve characteristic analysis, the system terminal identifies the key points on each curve. These key points include the extreme points, inflection points, etc. of the curve. Subsequently, by comparing and analyzing the key points of different curves, the verification dimensions are initially determined. These dimensions involve specific production links, raw material types, process parameters, etc., and their performances on different curves are significantly different. After initially determining the verification dimensions, the system terminal adjusts and improves the dimensions in combination with the actual production situation and historical data. For example, a certain production link can be further broken down into multiple sub-links, or multiple related process parameters can be combined into one dimension for verification. After refinement and optimization, the system terminal determines the verification dimensions. These dimensions can comprehensively cover the key influencing factors of product quality and provide clear guidance for the subsequent quality deviation coefficient test records. Further, the system terminal sets the parameter ranges, constraint conditions, initial states, etc. of each dimension according to the determined verification dimensions, and constructs a simulation environment. This simulation environment can accurately reflect the key factors in the actual production process. Subsequently, the system terminal inputs the quality deviation coefficient into the simulation environment, and the simulation environment will perform multiple simulation runs according to the deviation coefficients of multiple indicators in the quality deviation coefficient. In each run, observe and record the changes in the quality deviation coefficient under each dimension. Then, extract the recorded data from the simulation environment and organize it according to the dimensions to generate multi-dimensional verification results. These results show the specific values and change trends of the quality deviation coefficient under different dimensions, providing rich information for the system terminal to comprehensively judge the product quality status. In summary, this process aims to verify and analyze the quality deviation coefficient from multiple dimensions to obtain a more comprehensive and accurate product quality assessment result. This not only helps the system terminal deeply understand the root causes of product quality problems, but also provides strong data support for subsequent quality management.

[0040] Based on the multi-dimensional verification results, weight allocation is performed according to the first quality change curve, the second quality change curve, the third quality change curve, and the fourth quality change curve to generate a weight configuration result;

[0041] According to the weight configuration result, hierarchical division determination is carried out to generate the N quality management levels.

[0042] Optionally, the system terminal analyzes the specific performance of the quality deviation coefficients under each dimension of the multi-dimensional verification results, identifies the key features of each quality change curve, such as trends, fluctuation amplitudes, extreme points, etc. According to the quality management requirements, determine the key factors for weight allocation, such as the severity of quality problems, the scope of influence, the difficulty of solution, etc., and analyze the correlation between these key factors and the four quality change curves. In this way, the system terminal can more accurately determine the importance and priority of the quality problems represented by each curve in the overall quality management, and complete the weight allocation to obtain the weight configuration result. After completing the weight allocation, the system terminal further performs hierarchical division based on these weights, thereby generating multiple quality management levels. For example, curves with higher weight values are classified into higher levels to highlight their importance. Subsequently, sorting and classification are performed according to the weight configuration results so that similar curves can be grouped into the same level, thereby determining the final N quality management levels. Each quality management level contains quality change curves with similar weights and characteristics, which is convenient for targeted quality management and control.

[0043] Connect the N quality management levels according to the hierarchical association relationship to construct a quality management teacher model;

[0044] In one embodiment, the system terminal identifies and determines the association relationship between each quality management level based on the judgment of information flow. Subsequently, using the obtained association relationship, the N quality management levels are connected and integrated to obtain a quality management teacher model. Among them, each level is connected to each other through specific rules to ensure the consistency of data exchange formats. This model not only shows the hierarchical relationship between each quality management level, but also reveals the interaction and influence between them. Finally, this teacher model can be used to guide the practical work of quality management. It can help understand quality problems and assist the system terminal in obtaining the goodness-of-fit distillation result.

[0045] Furthermore, the present application provides a method for connecting the N quality management levels according to the hierarchical association relationship to construct a quality management teacher model, and the method further includes:

[0046] Determine the hierarchical association relationship between the N quality management levels based on mapping the information flow between the N quality management levels;

[0047] Preferably, the system terminal determines the hierarchical association relationship between N quality management levels based on mapping the information flow between them, which is a process of clarifying the logical relationship between levels by analyzing the transmission and interaction of information during parameter adjustment. In this process, the system terminal focuses on the information flow triggered during parameter adjustment. When adjusting a certain parameter, if this adjustment affects other parameters, there is a corresponding relationship between the affected parameter and the adjusted parameter. This corresponding relationship actually reveals the hierarchical association relationship existing between different quality management levels. By analyzing these corresponding relationships, the mutual influence and dependence relationships between quality management levels can be clarified. For example, a change in a parameter related to surface roughness in the surface roughness management level will affect a certain process in the surface finish management level that relies on this parameter. Through such information flow analysis, the system terminal can construct a more accurate quality management hierarchy. This structure not only reflects the logical relationship between levels but also provides an important reference when formulating and adjusting quality management strategies. Therefore, determining the hierarchical association relationship between quality management levels based on the mapping of information flow during parameter adjustment is a key step in deeply understanding the mutual influence and interaction between levels, which helps to more precisely implement quality management measures and improve the overall quality management level.

[0048] Construct a hierarchical connection rule according to the hierarchical association relationship, and connect the N quality management levels according to the hierarchical connection rule. The N quality management levels include a surface roughness management level, a surface warpage management level, a surface finish management level, and a surface coating uniformity management level.

[0049] Integrate the surface roughness management level, the surface warpage management level, the surface finish management level, and the surface coating uniformity management level to obtain the quality management teacher model.

[0050] Preferably, constructing the hierarchical connection rules according to the hierarchical association relationship is to achieve the effective connection between N quality management levels by formulating a unified data exchange standard. This can avoid duplicate labor and the occurrence of information silos, and ensure the consistency and accuracy of each quality management level in data transmission and sharing. Subsequently, the system terminal closely connects the N quality management levels together by following these hierarchical connection rules, and constructs the framework of the quality management teacher model. This framework can accommodate all management levels and support the interaction and collaboration between levels. After that, the functions of the connected quality management levels are integrated into the quality management teacher model to ensure that the functions can work together in the model to jointly achieve the quality management goal. Among them, the quality management teacher model includes the surface roughness management level, the surface warpage management level, the surface finish management level, and the surface coating uniformity management level. In the quality management teacher model, each level can share data in real time and cooperate with each other to jointly achieve the comprehensive monitoring and management of product quality. Under the unified data exchange standard, these levels can transmit relevant data on product surface quality in real time, jointly analyze the surface quality of the mold, and achieve efficient quality management, which helps the system terminal to more comprehensively understand the product quality status. Therefore, formulating a unified data exchange standard as the hierarchical connection rule is a key step to ensure the effective connection and collaboration between quality management levels, and helps to improve the overall quality management level.

[0051] Further, the present application provides a method for constructing hierarchical connection rules according to the hierarchical association relationship, and the method further includes:

[0052] Sequentially extract the shared data sets of the surface roughness management level, the surface warpage management level, the surface finish management level, and the surface coating uniformity management level based on the hierarchical association relationship;

[0053] Conduct cross-level collaborative analysis according to the shared data sets to construct collaborative framework information;

[0054] Sort out the connection process according to the collaborative framework information to formulate the hierarchical connection rules.

[0055] Optionally, the system terminal analyzes the hierarchical association relationships among the quality management levels. This includes understanding the input-output relationships and the degree of interdependence among the levels. By analyzing these association relationships, it determines which data is common to each level, i.e., the shared data set. Subsequently, based on the analysis results of the hierarchical association relationships, it identifies the data items that are of common concern to each level. These data items may involve basic measurement data on the product surface, historical quality problem records, etc. Then, it extracts the data related to the shared data set from the databases of the surface roughness management level, the surface warpage management level, the surface finish management level, and the surface coating uniformity management level in sequence, and stores it in the corresponding positions in the shared data set. This shared data set is the key information shared among the management levels, which reflects different aspects of product quality and is also the basis for cross-level collaborative analysis.

[0056] After obtaining the shared data set, the system terminal conducts in-depth analysis on the shared data set to reveal the relationships and interactions among the management levels in the quality control process. Subsequently, based on the results of the cross-level collaborative analysis, it designs the collaborative mechanism among the management levels, determines the specific implementation methods of the collaborative mechanism, including data sharing processes, collaborative decision-making mechanisms, problem feedback channels, etc., to eliminate duplicate labor, break information silos, and achieve resource sharing and efficient collaboration. Then, in combination with the design of the collaborative mechanism, it constructs detailed collaborative framework information. This includes clarifying the roles and responsibilities of each management level, collaborative work processes, information exchange standards, etc. This collaborative framework not only describes the logical relationships among the management levels but also provides guiding principles and methods for carrying out collaborative work.

[0057] After obtaining the collaborative framework information, the system terminal sorts out the connection processes among the management levels based on the collaborative framework information. This includes determining the data flow direction, information transmission paths, and key nodes of collaborative work to ensure that each management level can receive and send necessary information at the correct time point according to the process requirements and achieve seamless connection with other management levels. Subsequently, according to the sorted connection processes, it formulates specific hierarchical connection rules. The hierarchical connection rules clarify the data exchange standards, information sharing methods, decision support processes, etc. among the management levels. Then, after formulating the hierarchical connection rules, it verifies their feasibility through simulation experiments. This helps to discover possible problems or deficiencies in the rules and make timely adjustments. The verification process can also help each management level better understand and accept these rules and lay a foundation for subsequent collaborative work. Then, according to the verification results, it improves and optimizes the hierarchical connection rules, including adjusting the data exchange format, optimizing the information sharing process, or adding new collaborative mechanisms, etc., to ensure that the rules can adapt to the continuously changing quality control requirements and maintain their long-term effectiveness.

[0058] In summary, by extracting shared datasets, conducting cross-layer collaborative analysis, and formulating hierarchical connection rules, the system terminal has successfully constructed a hierarchical connection rule that can integrate the resources of each management layer and optimize the quality management process. This hierarchical connection rule provides strong support for improving product quality and enhancing the collaborative ability among different management layers.

[0059] The quality management teacher model is distilled and optimized through a knowledge distillation channel, and the knowledge distillation channel includes N distillation goodness branches;

[0060] In one embodiment, knowledge distillation is a model optimization technique whose core idea is to transfer the knowledge of a large and complex teacher model to a small and simple student model, so that the student model can reduce the computational cost and storage requirements while maintaining performance. During the process of distilling and optimizing the quality management teacher model, the system terminal uses a knowledge distillation channel that includes N distillation goodness branches. Specifically, the system terminal determines the knowledge distillation objectives that each of the N distillation goodness branches is responsible for. For example, the surface roughness branch will focus on extracting knowledge and features related to surface roughness from the teacher model; the surface warpage branch will focus on information related to warpage; the surface finish branch and the surface coating uniformity branch will respectively focus on knowledge of surface finish and coating uniformity. Subsequently, the network structure of each branch is designed, and specific convolutional layers, pooling layers, fully connected layers, etc. are designed according to the docked management layer to extract and encode the quality management features that each branch is concerned with. After that, the interfaces between the teacher model and each of the distillation goodness branches are defined to ensure that the output of the teacher model can be correctly input into each branch, and the data flow is designed so that the output of the teacher model can flow to the corresponding distillation goodness branches respectively. Through the above process, the system terminal successfully constructs N distillation goodness branches. Then, the system terminal optimizes each management layer in the quality management teacher model through these distillation goodness branches to obtain the corresponding optimization results. In this way, the subsequent student model can quickly absorb the essence of the teacher model in quality management and demonstrate performance similar to or even better than the teacher model in practical applications. At the same time, since the scale of the student model is smaller, it is easier to be deployed in an environment with limited resources, providing greater convenience for actual production. In summary, by distilling and optimizing the quality management teacher model through the knowledge distillation channel, the lightweighting and performance improvement of the model are successfully achieved, injecting new vitality into the development of the quality management field.

[0061] Data distillation is performed on the N quality management layers through the N distillation goodness branches to obtain N goodness distillation results;

[0062] In one embodiment, the system terminal performs data distillation on N different quality management levels in the quality management teacher model through the constructed N distillation goodness branches. Each branch targets a specific quality management level and is responsible for extracting and encoding the key knowledge and features of that level. Through distillation, the system terminal obtains N goodness distillation results, which represent the essence of the knowledge and experience transferred from the teacher model to the student model. These results not only retain the performance advantages of the teacher model but also optimize the computational efficiency and storage space through the simplified structure of the student model. In summary, through data distillation using N distillation goodness branches, the key knowledge of multiple quality management levels can be effectively extracted from the teacher model and transformed into a form understandable by the student model, improving the performance of the student model.

[0063] Furthermore, the present application provides a method for performing data distillation on the N quality management levels through the N distillation goodness branches to obtain N goodness distillation results, and the method further includes:

[0064] Performing distillation optimization on the surface roughness management level in the quality management teacher model through the surface roughness distillation goodness branch in the knowledge distillation channel to obtain a surface roughness goodness distillation result;

[0065] Performing distillation optimization on the surface warpage management level through the surface warpage distillation goodness branch to obtain a surface warpage goodness distillation result;

[0066] Performing distillation optimization on the surface finish management level through the surface finish distillation goodness branch to obtain a surface finish goodness distillation result;

[0067] Performing distillation optimization on the surface coating uniformity management level through the surface coating uniformity distillation goodness branch to obtain a surface coating uniformity goodness distillation result;

[0068] Preferably, the system terminal optimizes the distillation of different management levels in the quality management teacher model through the constructed knowledge distillation channel, using four specific distillation goodness branches respectively. These branches are the distillation goodness branches for surface roughness, surface warpage, surface finish, and surface coating uniformity. First, the surface roughness distillation goodness branch extracts key knowledge and features from the surface roughness management level of the teacher model, and uses the extracted data as soft labels, which contain the rich knowledge and experience of the teacher model in surface roughness recognition. Subsequently, the weight distribution and connection methods of each neuron in the surface roughness management level are analyzed. Determine which weights are crucial for the recognition of surface roughness, and mark the key weights that need to be optimized. Then, the surface roughness distillation goodness branch adjusts the weights of relevant neurons in the surface roughness management level according to the extracted key features. For example, give higher weights to neurons that respond strongly to key features to enhance the model's ability to recognize surface roughness, or use the gradient descent algorithm to fine-tune these weights to improve the recognition performance of surface roughness. Then, the optimized surface roughness management level is output as the surface roughness goodness distillation result. This result reflects the performance advantages of the teacher model in terms of surface roughness and is successfully transmitted to the student model. Secondly, the surface warpage distillation goodness branch performs a similar distillation optimization process on the surface warpage management level and obtains the goodness distillation result of surface warpage. This result also retains the excellent performance of the teacher model in this regard. Similarly, the surface finish distillation goodness branch performs the same distillation optimization on the surface finish management level, extracts the key knowledge and experience related to surface finish, and forms the goodness distillation result of surface finish. Finally, the surface coating uniformity distillation goodness branch performs distillation optimization on the surface coating uniformity management level and obtains the goodness distillation result of surface coating uniformity. This result reflects the professional knowledge and experience of the teacher model in terms of coating uniformity. Through the collaborative work of these four distillation goodness branches, the key knowledge and experience regarding surface roughness, surface warpage, surface finish, and surface coating uniformity are successfully distilled from the teacher model and corresponding goodness distillation results are formed. These results not only improve the performance of the student model at the corresponding quality management level but also provide strong support for further model optimization and application.

[0069] Determine the N goodness distillation results based on the surface roughness goodness distillation result, the surface warpage goodness distillation result, the surface finish goodness distillation result, and the surface coating uniformity goodness distillation result.

[0070] Preferably, based on the obtained surface roughness goodness distillation result, surface warpage goodness distillation result, surface finish goodness distillation result, and surface coating uniformity goodness distillation result, the system terminal regards these goodness distillation results as a quantitative manifestation of the optimization effect of the quality management teacher model in surface quality assessment. These goodness distillation results are obtained through the optimization of relevant management levels within the teacher model, and they respectively reflect the performance improvement of the model in identifying key quality features such as surface roughness, warpage, finish, and coating uniformity. By synthesizing these N goodness distillation results, a comprehensive evaluation of the overall optimization effect of the model can be conducted. These results not only show the degree of optimization of the model in individual quality features but also provide the performance of the model in comprehensive quality assessment. By comparing the results before and after optimization, the improvement degree of the model in surface quality assessment can be quantitatively understood, thus better guiding subsequent quality management work. In summary, these N goodness distillation results are quantitative indicators of the optimization effect of the quality management teacher model in surface quality assessment, and they jointly constitute a comprehensive evaluation of the model's comprehensive performance.

[0071] Construct a quality management student model based on the N goodness distillation results, and optimize the surface quality of the target stator core mold through the quality management student model.

[0072] In one embodiment, the system terminal constructs a quality management student model based on the obtained N goodness distillation results using a BP (backpropagation) neural network and optimizes it through a preset distillation loss calculation formula. This quality management student model is inspired by the knowledge optimized by the teacher model and integrates the goodness distillation results of multiple key quality features such as surface roughness, warpage, finish, and coating uniformity. These goodness distillation results not only contain the experience of the quality management teacher model in identifying these quality features but also reflect the learning achievements of the quality management teacher model during the optimization process. By using the quality management student model, the system terminal can optimize the surface quality of the target stator core mold. The quality management student model can accurately evaluate the surface quality of the stator core mold by using the key knowledge and features distilled from the quality management teacher model. Based on these evaluation results, potential problems on the mold surface can be discovered, and corresponding optimization measures can be taken, such as adjusting processing parameters, improving coating processes, etc., to improve the surface quality of the mold. In summary, by constructing a quality management student model and applying the N goodness distillation results, the optimization management of the surface quality of the target stator core mold can be achieved, and the product quality can be improved.

[0073] Furthermore, before inputting the frost area distribution and frost thickness into the defrost control analysis module for analysis and processing, the method further includes:

[0074] Based on the BP neural network, construct a quality management student model through the N goodness-of-fit distillation results;

[0075] Calculate and output a distillation loss data set based on the distillation loss calculation formula;

[0076] Preferably, the system terminal constructs a quality management student model based on the BP neural network using the N goodness-of-fit distillation results, enabling it to learn the key knowledge and features distilled from the teacher model. The BP neural network is a powerful learning algorithm that adjusts the network weights through backpropagation of errors to achieve classification or regression of input data. Specifically, the system terminal first determines the network structure of the quality management student model, including the number of nodes in the input layer, hidden layer, and output layer. Then, based on the number of feature quantities of the N goodness-of-fit distillation results, the number of nodes in the input layer is determined. Subsequently, according to the complexity of the problem and the characteristics of the data, the appropriate number of hidden layers and nodes is selected, and the number of nodes in the output layer is corresponded to the number of quality management indicators. After that, initial values are randomly assigned to the connection weights in the neural network. Then, the N goodness-of-fit distillation results are used as input data, and the output of the network is calculated through the forward propagation algorithm. Then, the error between the network output and the output of the teacher model is calculated. Using the backpropagation algorithm, the error is propagated backward from the output layer to the input layer, and the weights between the nodes of each layer are adjusted according to the magnitude of the error. Finally, the forward propagation and backpropagation processes are repeated, and the weights are iteratively updated until the preset maximum number of iterations is reached, and the constructed quality management student model is output.

[0077] After obtaining the quality management student model, the system terminal calculates the distillation loss using the pre-set distillation loss calculation formula. The distillation loss is an indicator that measures the difference between the outputs of the student model and the teacher model. By comparing the outputs of the two, a loss value is calculated, which reflects the performance of the student model when mimicking the teacher model. The distillation loss calculation formula is designed based on the difference between the two outputs to ensure that the student model can be as close as possible to the performance of the teacher model. Through calculation, the system terminal successfully obtains a distillation loss data set. This distillation loss data set will be used to further adjust and optimize the parameters of the student model. Through iterative training, the distillation loss can be continuously reduced, thereby improving the performance of the student model.

[0078] In summary, based on the BP neural network, the quality management student model can be constructed and evaluated according to the calculation results obtained from the distillation loss calculation formula, enabling it to make full use of the N goodness-of-fit distillation results to improve the management effect of the surface quality of the target stator core mold.

[0079] Evaluate the effectiveness of the quality management student model according to the distillation loss data set, and generate an effective evaluation result;

[0080] Optimize the quality management student model according to the effective evaluation result.

[0081] Preferably, during the process of optimizing the quality management student model, the distillation loss dataset is of great significance. This dataset is used to measure the performance difference of the student model when mimicking the teacher model. By storing the error between the outputs of the two, that is, the distillation loss. This loss value reflects the effect of the student model in learning and inheriting the knowledge of the teacher model. To evaluate the effectiveness of the quality management student model, the system terminal conducts in-depth analysis using the distillation loss dataset. By observing the magnitude and change trend of the loss value, it is judged whether the performance of the student model meets the expectations and whether there is room for further optimization. A smaller distillation loss value indicates that the student model can better approximate the performance of the teacher model, indicating a higher effectiveness of the model. Based on the effective evaluation result, the system terminal optimizes the quality management student model specifically. If the distillation loss is large, it means that the student model still has deficiencies in some aspects and needs further optimization. At this time, the system terminal tries strategies such as adjusting the network structure of the model, increasing the number of hidden layer nodes, and changing the learning rate to improve the performance of the model. By continuously optimizing the quality management student model, it can better adapt to the actual quality management requirements and improve the optimization management level of the surface quality of the stator core mold. In summary, using the distillation loss dataset to evaluate the effectiveness of the quality management student model and optimizing according to the evaluation result are the key steps to improve the model performance and achieve high-quality management.

[0082] Furthermore, the present application provides a distillation loss calculation formula, and the method further includes:

[0083] ;

[0084] where, is the distillation loss, is the weight factor, is the smoothed probability distribution, is any one category, is the quality management teacher model, is the quality management student model, is the output probability distribution of the quality management teacher model, is the output probability distribution of the quality management student model.

[0085] Optionally, the distillation loss calculation formula is specifically as follows:

[0086] ;

[0087] where, represents the distillation loss (Distillation Loss) function, which measures the student model During the imitation of the teacher model when there is a performance gap. Here refers to the quality metric between the teacher model and the student model. Specifically is a weight factor used to adjust the influence degree of the distillation loss in the overall loss function. It can be adjusted according to the needs of specific tasks to balance the importance of different loss terms. represents the smoothed probability distribution, which is used to soften the output of the teacher model to make it easier for the student model to learn. The smoothing process helps prevent the student model from overfitting to the hard label output of the teacher model. refers to the logarithm of the output probability distribution of the teacher model for the -th class, which is convenient for calculating the loss. The system terminal first calculates the logarithm of the output probability distribution of the teacher model for each sample or class, then multiplies these logarithms by the weight factor and the square of the smoothed probability distribution, and finally sums up the weighted logarithms of all samples to obtain the overall distillation loss. The purpose of this formula is to quantify the performance of the student model during the imitation process by comparing the output probability distributions of the teacher model and the student model, and to improve the accuracy and generalization ability of the student model by optimizing the distillation loss, so as to achieve more efficient model training and performance improvement.

[0088] In summary, the embodiments of the present application at least have the following technical effects:

[0089] In the embodiments of the present application, the quality deviation coefficient is obtained through surface quality detection, and based on this coefficient, multi-dimensional verification is carried out to obtain N quality management levels. Subsequently, these quality management levels are connected according to the hierarchical association relationship to construct a quality management teacher model. Then, the teacher model is optimized through knowledge distillation to generate N goodness distillation results, and a quality management student model is constructed. Then, the effectiveness of the student model is evaluated using a BP neural network, and the model is optimized according to the evaluation results. This method improves the surface quality of the stator core mold through a multi-level and multi-dimensional management and optimization process, achieving efficient quality management. These technical effects together solve the technical problems that traditional detection methods often rely on manual experience and visual observation, only focus on the roughness and smoothness of the mold surface, and it is difficult to accurately evaluate the actual quality of the mold surface, resulting in low accuracy and stability of quality management. Through comprehensive measures in multiple links such as the knowledge distillation channel and the quality management teacher model, the technical effects of improving the surface quality of the mold and improving the accuracy and efficiency of quality management are achieved.

[0090] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the particular order and sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0092] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A surface quality management method for a stator core mold, characterized in that: The method comprises: Conduct surface quality inspection on the target stator core mold to obtain the quality deviation coefficient; Perform multi-dimensional verification based on the quality deviation coefficient and output N quality management layers, where N is an integer greater than or equal to 1; Connect the N quality management layers according to the hierarchical association relationship to build a quality management teacher model; Distill and optimize the quality management teacher model through a knowledge distillation channel, wherein the knowledge distillation channel includes N distillation goodness branches; Performing data distillation on the N quality management layers through the N distillation goodness branches to obtain N goodness distillation results; A quality management student model is constructed based on the N goodness distillation results, and the surface quality of the target stator core mold is optimized by the quality management student model; The N quality management layers are connected according to the hierarchical association relationship to construct a quality management teacher model, and the method includes: Determining the hierarchical association relationship between the N quality management layers based on mapping the information flow between the N quality management layers; Constructing a hierarchical connection rule according to the hierarchical association relationship, and connecting the N quality management layers according to the hierarchical connection rule, wherein the N quality management layers include a surface roughness management layer, a surface warpage management layer, a surface finish management layer, and a surface coating uniformity management layer; Integrate the surface roughness management layer, the surface warpage management layer, the surface finish management layer, and the surface coating uniformity management layer to obtain the quality management teacher model; The method for constructing a hierarchical connection rule according to the hierarchical association relationship includes: Based on the hierarchical association relationship, the shared data sets of the surface roughness management layer, the surface warpage management layer, the surface finish management layer, and the surface coating uniformity management layer are sequentially extracted; Perform cross-layer collaborative analysis based on the shared data set to construct collaborative framework information; The connection process is sorted out according to the collaborative framework information, and the hierarchical connection rules are formulated.

2. A surface quality management method for a stator core mold according to claim 1, characterized in that: Perform surface quality inspection on the target stator core mold to obtain the quality deviation coefficient. The method includes: Traversing the qualified mold parameters of the stator core of the big data, formulating the surface quality inspection standard of the target stator core mold, wherein the surface quality inspection standard includes a preset roughness standard, a preset warpage standard, a preset smoothness standard, and a preset coating uniformity standard; In the first detection phase, the target stator core mold is detected based on the preset roughness standard to generate a first detection result; In the second detection phase, the target stator core mold is detected based on the preset warpage standard to generate a second detection result; In the third detection stage, the target stator core mold is detected based on the preset smoothness standard to generate a third detection result; In the fourth detection stage, the target stator core mold is detected based on the preset coating uniformity standard to generate a fourth detection result; Integrate the first test result, the second test result, the third test result, and the fourth test result to perform deviation calculation to generate first mass deviation data, second mass deviation data, third mass deviation data, and fourth mass deviation data; The first mass deviation data, the second mass deviation data, the third mass deviation data, and the fourth mass deviation data are added to the mass deviation coefficient.

3. A surface quality management method for a stator core mold according to claim 2, characterized in that: Based on the quality deviation coefficient, multi-dimensional verification is performed to output N quality management layers, and the method includes: Respectively analyzing the change trends of the first mass deviation data, the second mass deviation data, the third mass deviation data, and the fourth mass deviation data to obtain a first mass change curve, a second mass change curve, a third mass change curve, and a fourth mass change curve; Determine a verification dimension based on the first quality change curve, the second quality change curve, the third quality change curve, and the fourth quality change curve; Testing and recording the quality deviation coefficient according to the verification dimension to generate a multi-dimensional verification result; Based on the multi-dimensional verification result, weight allocation is performed according to the first mass change curve, the second mass change curve, the third mass change curve, and the fourth mass change curve to generate a weight configuration result; The hierarchical division is determined according to the weight configuration result to generate the N quality management layers.

4. A surface quality management method for a stator core mold according to claim 1, characterized in that: The N quality management layers are subjected to data distillation through the N distillation goodness branches to obtain N goodness distillation results, the method comprising: The surface roughness management layer in the quality management teacher model is distilled and optimized through the surface roughness distillation goodness branch in the knowledge distillation channel to obtain a surface roughness goodness distillation result; The surface warpage management layer is distilled and optimized through a surface warpage distillation goodness branch to obtain a surface warpage goodness distillation result; Performing distillation optimization on the surface finish management layer through the surface finish distillation goodness branch to obtain a surface finish goodness distillation result; The surface coating uniformity management layer is distilled and optimized through a surface coating uniformity distillation goodness branch to obtain a surface coating uniformity goodness distillation result; The N goodness distillation results are determined based on the surface roughness goodness distillation result, the surface warpage goodness distillation result, the surface smoothness goodness distillation result, and the surface coating uniformity goodness distillation result.

5. The surface quality management method of a stator core mold according to claim 1, characterized in that: Methods include: Based on the BP neural network, a quality management student model is constructed through the N goodness distillation results; Calculate and output the distillation loss data set based on the distillation loss calculation formula; Evaluating the effectiveness of the quality management student model based on the distillation loss data set to generate effective evaluation results; Optimizing the quality management student model according to the effective evaluation results.

6. A surface quality management method for a stator core mold according to claim 5, characterized in that: The distillation loss calculation formula is: ； in, is the distillation loss, is the weight factor, is a smooth probability distribution, For any category, For the quality management teacher model, For the quality management student model, is the output probability distribution of the quality management teacher model, Output probability distribution of the quality management student model.

Images